Skip to main content
Glama

claude_prompt

Build a Claude CLI command with mode-based model defaults, gateway routing, and tiered failover; returns JSON for agent shell execution.

Instructions

Build a Claude CLI command with intelligent work-to-model mode defaults, gateway routing, and 3-tier failover cascade. INSTRUCTION: Call claude_models first to discover supported models before calling this tool. Supports Red Hat EnMaaS AI Gateway (free GLM 5.3) and GCP Vertex AI (canonical sonnet, opus, claude-sonnet-5, claude-opus-4-8) with shared-quota bypass and tertiary fallback. Returns JSON { command, cwd, description, block_until_ms } for agent shell execution.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "claude_prompt"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoWorking directory for Claude CLI
modeNoDispatch mode: architect, planner, reviewer, explorer, executor.
modelNoExact model name (e.g. sonnet, opus, rits/zai-org/glm-5-3, claude-sonnet-5, claude-opus-4-8). Overrides mode default.
effortNoReasoning effort level.
promptYesThe prompt to send to Claude
projectNoAlias for primaryProject.
providerNoInference provider: "auto" (default), "enmaas" (requires ENMAAS_KEY), or "vertex".auto
sessionIdNoResume a previous session by ID
credentialsNoAlias for primaryCredentials.
systemPromptNoSystem prompt override (--system-prompt).
tertiaryModelNoFallback model name for tertiary failover (defaults to sonnet).
primaryProjectNoPrimary GCP project ID for Vertex AI execution.
secondaryModelNoFallback model name for cross-provider failover (defaults to sonnet).
tertiaryProjectNoTertiary GCP project ID for isolated quota failover.
secondaryProjectNoSecondary GCP project ID for automatic quota/budget failover.
primaryCredentialsNoPath to primary GCP service account credentials JSON.
tertiaryCredentialsNoPath to tertiary GCP service account credentials JSON.
secondaryCredentialsNoPath to secondary GCP service account credentials JSON.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.8.0

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does most of it: it discloses the return shape and that the output is meant 'for agent shell execution', which is the critical safety-relevant fact. It also explains the three-tier failover, shared-quota bypass, and provider prerequisites. It leaves out whether malformed model names are validated before returning, and whether any network call happens at build time.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each with a distinct job: purpose, prerequisite instruction, supported providers/failover, return value. The prerequisite is capitalized and positioned early, ahead of the provider detail, with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 18-parameter tool with no annotations and no output schema, the description supplies the return shape, the prerequisite call, the provider matrix, and the failover model. That covers what an agent needs to invoke it correctly. Residual gaps are narrow: whether the tool performs any I/O, and how conflicting mode/model inputs resolve.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description earns above that by explaining the structure the individual parameters only hint at: the 3-tier cascade that gives secondary/tertiary model, project, and credentials fields their meaning, plus 'work-to-model mode defaults' explaining how mode maps to model. It still does not say how mode defaults interact with an explicit model or effort.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and artifact: 'Build a Claude CLI command' with mode defaults, gateway routing, and a failover cascade, and the closing sentence clarifies it returns { command, cwd, description, block_until_ms } rather than executing anything. That is enough to separate it from claude_models. It stops short of a crisp one-line 'this composes a command, it does not run it' framing, so an agent must read to the final sentence to be certain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit prerequisite in caps: call claude_models first to discover supported models. It also signals when each provider path applies (enmaas requires ENMAAS_KEY, vertex uses canonical model names). It does not state when NOT to use the tool or how to choose between providers beyond the 'auto' default, so guidance is strong but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools